diff --git a/include/linux/slab.h b/include/linux/slab.h
index 573c809..a595dce 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -190,7 +190,7 @@
 #endif
 
 /**
- * kcalloc - allocate memory for an array. The memory is set to zero.
+ * kmalloc_array - allocate memory for an array.
  * @n: number of elements.
  * @size: element size.
  * @flags: the type of memory to allocate.
@@ -240,11 +240,22 @@
  * for general use, and so are not documented here. For a full list of
  * potential flags, always refer to linux/gfp.h.
  */
-static inline void *kcalloc(size_t n, size_t size, gfp_t flags)
+static inline void *kmalloc_array(size_t n, size_t size, gfp_t flags)
 {
 	if (size != 0 && n > ULONG_MAX / size)
 		return NULL;
-	return __kmalloc(n * size, flags | __GFP_ZERO);
+	return __kmalloc(n * size, flags);
+}
+
+/**
+ * kcalloc - allocate memory for an array. The memory is set to zero.
+ * @n: number of elements.
+ * @size: element size.
+ * @flags: the type of memory to allocate (see kmalloc).
+ */
+static inline void *kcalloc(size_t n, size_t size, gfp_t flags)
+{
+	return kmalloc_array(n, size, flags | __GFP_ZERO);
 }
 
 #if !defined(CONFIG_NUMA) && !defined(CONFIG_SLOB)
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index ca122b3..c2f8c8b 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -22,7 +22,7 @@
 	FREE_FROZEN,		/* Freeing to frozen slab */
 	FREE_ADD_PARTIAL,	/* Freeing moves slab to partial list */
 	FREE_REMOVE_PARTIAL,	/* Freeing removes last object */
-	ALLOC_FROM_PARTIAL,	/* Cpu slab acquired from partial list */
+	ALLOC_FROM_PARTIAL,	/* Cpu slab acquired from node partial list */
 	ALLOC_SLAB,		/* Cpu slab acquired from page allocator */
 	ALLOC_REFILL,		/* Refill cpu slab from slab freelist */
 	ALLOC_NODE_MISMATCH,	/* Switching cpu slab */
@@ -38,7 +38,9 @@
 	CMPXCHG_DOUBLE_CPU_FAIL,/* Failure of this_cpu_cmpxchg_double */
 	CMPXCHG_DOUBLE_FAIL,	/* Number of times that cmpxchg double did not match */
 	CPU_PARTIAL_ALLOC,	/* Used cpu partial on alloc */
-	CPU_PARTIAL_FREE,	/* USed cpu partial on free */
+	CPU_PARTIAL_FREE,	/* Refill cpu partial on free */
+	CPU_PARTIAL_NODE,	/* Refill cpu partial from node partial */
+	CPU_PARTIAL_DRAIN,	/* Drain cpu partial to node partial */
 	NR_SLUB_STAT_ITEMS };
 
 struct kmem_cache_cpu {
diff --git a/mm/slab.c b/mm/slab.c
index 29c8716..e901a36 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1731,6 +1731,52 @@
 }
 __initcall(cpucache_init);
 
+static noinline void
+slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid)
+{
+	struct kmem_list3 *l3;
+	struct slab *slabp;
+	unsigned long flags;
+	int node;
+
+	printk(KERN_WARNING
+		"SLAB: Unable to allocate memory on node %d (gfp=0x%x)\n",
+		nodeid, gfpflags);
+	printk(KERN_WARNING "  cache: %s, object size: %d, order: %d\n",
+		cachep->name, cachep->buffer_size, cachep->gfporder);
+
+	for_each_online_node(node) {
+		unsigned long active_objs = 0, num_objs = 0, free_objects = 0;
+		unsigned long active_slabs = 0, num_slabs = 0;
+
+		l3 = cachep->nodelists[node];
+		if (!l3)
+			continue;
+
+		spin_lock_irqsave(&l3->list_lock, flags);
+		list_for_each_entry(slabp, &l3->slabs_full, list) {
+			active_objs += cachep->num;
+			active_slabs++;
+		}
+		list_for_each_entry(slabp, &l3->slabs_partial, list) {
+			active_objs += slabp->inuse;
+			active_slabs++;
+		}
+		list_for_each_entry(slabp, &l3->slabs_free, list)
+			num_slabs++;
+
+		free_objects += l3->free_objects;
+		spin_unlock_irqrestore(&l3->list_lock, flags);
+
+		num_slabs += active_slabs;
+		num_objs = num_slabs * cachep->num;
+		printk(KERN_WARNING
+			"  node %d: slabs: %ld/%ld, objs: %ld/%ld, free: %ld\n",
+			node, active_slabs, num_slabs, active_objs, num_objs,
+			free_objects);
+	}
+}
+
 /*
  * Interface to system's page allocator. No need to hold the cache-lock.
  *
@@ -1757,8 +1803,11 @@
 		flags |= __GFP_RECLAIMABLE;
 
 	page = alloc_pages_exact_node(nodeid, flags | __GFP_NOTRACK, cachep->gfporder);
-	if (!page)
+	if (!page) {
+		if (!(flags & __GFP_NOWARN) && printk_ratelimit())
+			slab_out_of_memory(cachep, flags, nodeid);
 		return NULL;
+	}
 
 	nr_pages = (1 << cachep->gfporder);
 	if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
@@ -3696,13 +3745,12 @@
 
 	if (likely(ac->avail < ac->limit)) {
 		STATS_INC_FREEHIT(cachep);
-		ac->entry[ac->avail++] = objp;
-		return;
 	} else {
 		STATS_INC_FREEMISS(cachep);
 		cache_flusharray(cachep, ac);
-		ac->entry[ac->avail++] = objp;
 	}
+
+	ac->entry[ac->avail++] = objp;
 }
 
 /**
diff --git a/mm/slub.c b/mm/slub.c
index f4a6229..64d9966 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -29,6 +29,7 @@
 #include <linux/math64.h>
 #include <linux/fault-inject.h>
 #include <linux/stacktrace.h>
+#include <linux/prefetch.h>
 
 #include <trace/events/kmem.h>
 
@@ -269,6 +270,11 @@
 	return *(void **)(object + s->offset);
 }
 
+static void prefetch_freepointer(const struct kmem_cache *s, void *object)
+{
+	prefetch(object + s->offset);
+}
+
 static inline void *get_freepointer_safe(struct kmem_cache *s, void *object)
 {
 	void *p;
@@ -1560,6 +1566,7 @@
 		} else {
 			page->freelist = t;
 			available = put_cpu_partial(s, page, 0);
+			stat(s, CPU_PARTIAL_NODE);
 		}
 		if (kmem_cache_debug(s) || available > s->cpu_partial / 2)
 			break;
@@ -1983,6 +1990,7 @@
 				local_irq_restore(flags);
 				pobjects = 0;
 				pages = 0;
+				stat(s, CPU_PARTIAL_DRAIN);
 			}
 		}
 
@@ -1994,7 +2002,6 @@
 		page->next = oldpage;
 
 	} while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) != oldpage);
-	stat(s, CPU_PARTIAL_FREE);
 	return pobjects;
 }
 
@@ -2319,6 +2326,8 @@
 		object = __slab_alloc(s, gfpflags, node, addr, c);
 
 	else {
+		void *next_object = get_freepointer_safe(s, object);
+
 		/*
 		 * The cmpxchg will only match if there was no additional
 		 * operation and if we are on the right processor.
@@ -2334,11 +2343,12 @@
 		if (unlikely(!this_cpu_cmpxchg_double(
 				s->cpu_slab->freelist, s->cpu_slab->tid,
 				object, tid,
-				get_freepointer_safe(s, object), next_tid(tid)))) {
+				next_object, next_tid(tid)))) {
 
 			note_cmpxchg_failure("slab_alloc", s, tid);
 			goto redo;
 		}
+		prefetch_freepointer(s, next_object);
 		stat(s, ALLOC_FASTPATH);
 	}
 
@@ -2475,9 +2485,10 @@
 		 * If we just froze the page then put it onto the
 		 * per cpu partial list.
 		 */
-		if (new.frozen && !was_frozen)
+		if (new.frozen && !was_frozen) {
 			put_cpu_partial(s, page, 1);
-
+			stat(s, CPU_PARTIAL_FREE);
+		}
 		/*
 		 * The list lock was not taken therefore no list
 		 * activity can be necessary.
@@ -3939,13 +3950,14 @@
 		if (kmem_cache_open(s, n,
 				size, align, flags, ctor)) {
 			list_add(&s->list, &slab_caches);
+			up_write(&slub_lock);
 			if (sysfs_slab_add(s)) {
+				down_write(&slub_lock);
 				list_del(&s->list);
 				kfree(n);
 				kfree(s);
 				goto err;
 			}
-			up_write(&slub_lock);
 			return s;
 		}
 		kfree(n);
@@ -5069,6 +5081,8 @@
 STAT_ATTR(CMPXCHG_DOUBLE_FAIL, cmpxchg_double_fail);
 STAT_ATTR(CPU_PARTIAL_ALLOC, cpu_partial_alloc);
 STAT_ATTR(CPU_PARTIAL_FREE, cpu_partial_free);
+STAT_ATTR(CPU_PARTIAL_NODE, cpu_partial_node);
+STAT_ATTR(CPU_PARTIAL_DRAIN, cpu_partial_drain);
 #endif
 
 static struct attribute *slab_attrs[] = {
@@ -5134,6 +5148,8 @@
 	&cmpxchg_double_cpu_fail_attr.attr,
 	&cpu_partial_alloc_attr.attr,
 	&cpu_partial_free_attr.attr,
+	&cpu_partial_node_attr.attr,
+	&cpu_partial_drain_attr.attr,
 #endif
 #ifdef CONFIG_FAILSLAB
 	&failslab_attr.attr,